prizmkit 1.1.131 → 1.1.134

package/bundled/dev-pipeline/templates/refactor-bootstrap-prompt.md

@@ -187,7 +187,7 @@ Record tool choice, URL, steps, screenshot path if available, result, and cleanu
 
 ### Headless Commit Authorization
 
-This pipeline launch authorizes one local task commit only after review, authoritative test evidence, and required behavior-preservation gates pass. Never ask a question, wait for input, or request confirmation. Invoke `/prizmkit-committer` with `mode=l4-headless`, `owner=prizmkit-l4`, `local_commit_authorized=true`, and `push_authorized=false`. Never push.
+This pipeline launch authorizes one local task commit only after review, authoritative test evidence, and required behavior-preservation gates pass. Never ask a question, wait for input, or request confirmation. Invoke `/prizmkit-committer` with `mode=l4-headless`, `owner=prizmkit-l4`, and `local_commit_authorized=true`. The runtime controls any optional remote publication after the local commit; do not make a publication decision in this session.
 
 Run `/prizmkit-retrospective` using the current working tree and staged changes as input context. Do not rely only on `git diff --cached`.
 
@@ -199,7 +199,7 @@ Run `/prizmkit-committer` with commit prefix:
 refactor({{REFACTOR_ID}}): {{REFACTOR_TITLE}}
 ```
 
-Do not push.
+The runtime controls any optional remote publication after this local commit; do not make a publication decision in this session.
 
 Write `.prizmkit/refactor/{{REFACTOR_ID}}/refactor-report.md` with:
 - refactor summary;
@@ -267,7 +267,7 @@ Before exiting, write `{{SESSION_STATUS_PATH}}`:
 ## Reminders
 
 - Use L1 skills: `/prizmkit-plan`, `/prizmkit-implement`, `/prizmkit-code-review`, `/prizmkit-retrospective`, `/prizmkit-committer`.
-- Do not spawn a top-level Dev implementation subagent; Code Review runs only in the current Main Agent without delegation.
+- Do not spawn a top-level Dev implementation subagent; Code Review keeps mandatory Main-Agent ownership and may use only its strict-gated skill-owned Reviewer after convergence.
 - Behavior preservation is the first priority.
 - Browser verification is a mandatory attempt by default; it blocks only when explicitly required.
 - If `DEV_PORT` is unknown, discover it from project config; do not guess port 3000.

package/bundled/dev-pipeline/templates/sections/bugfix-phase-commit-report.md

@@ -1,6 +1,6 @@
 ### Phase 4: Commit & Learn
 
-This phase is included only for sessions allowed to commit. Fresh manual/hybrid bugfix prompts omit this phase entirely and stop as partial before retrospective/commit.
+This phase follows successful automated, manual, or hybrid verification and runs only after the authoritative test gate permits commit.
 
 **Bug Fix Documentation Policy**:
 - Default: run `/prizmkit-retrospective` with structural sync only.
@@ -17,7 +17,7 @@ Run `/prizmkit-committer` with commit prefix:
 fix({{FIX_SCOPE}}): {{BUG_TITLE}}
 ```
 
-Do not push.
+The runtime controls any optional remote publication after this local commit; do not make a publication decision in this session.
 
 Write `.prizmkit/bugfix/{{BUG_ID}}/fix-report.md` with:
 - root cause summary;

package/bundled/dev-pipeline/templates/sections/bugfix-phase-manual-verification.md

@@ -2,14 +2,9 @@
 
 `verification_type` is `{{VERIFICATION_TYPE}}`.
 
-For a fresh bugfix session, manual/hybrid verification is blocking before commit:
+L4 is always headless and must complete manual/hybrid verification automatically. Do not ask for a user, wait for UAT, or stop as `partial`.
 
-1. Write `{{SESSION_STATUS_PATH}}` with:
-   - `status`: `partial`
-   - `can_resume`: `true`
-   - `resume_from_phase`: `4`
-   - explanation that manual UAT is required before commit
-2. Document the UAT checklist in `.prizmkit/bugfix/{{BUG_ID}}/fix-report.md` or `failure-log.md`.
-3. Stop before `/prizmkit-retrospective` and `/prizmkit-committer`.
-
-Recovery-class sessions (retry, resume, continuation, context overflow) may substitute automated verification for manual/hybrid UAT, but must document the substitution evidence before committing.
+1. Select the available non-interactive verification path: browser tooling, CLI/API checks, fixtures, project test commands, or another deterministic local check.
+2. Cover the reported behavior and acceptance criteria; for browser-visible behavior, capture both the original reproduction and post-fix result when the configured tooling is available.
+3. Record the selected verification method, commands/tool, inputs, outputs, limitations, and evidence paths in `.prizmkit/bugfix/{{BUG_ID}}/fix-report.md` and the session/checkpoint metadata.
+4. Continue through the authoritative `prizmkit-test` gate, `/prizmkit-retrospective`, and `/prizmkit-committer` when all gates pass. Missing or blocked verification evidence is `TEST_BLOCKED`, not a request for user input.

package/bundled/dev-pipeline/templates/sections/bugfix-phase-review.md

@@ -2,13 +2,13 @@
 
 Code review is mandatory for every committable Bugfix, including small or obvious fixes. Do not create a FAST_PATH that skips this gate.
 
-Run `/prizmkit-code-review` with `artifact_dir=.prizmkit/bugfix/{{BUG_ID}}/`. The skill runs a Main-Agent review loop for up to ten completed rounds. The current Main Agent is the only Code Review executor: it reviews the complete current change, rejects unsupported candidate findings, directly repairs accepted findings, verifies repairs, and repeats until `accepted = 0` with no unresolved findings.
+Run `/prizmkit-code-review` with `artifact_dir=.prizmkit/bugfix/{{BUG_ID}}/`. The skill runs a mandatory Main-Agent review loop for up to ten completed rounds: the Main Agent reviews the complete current change, rejects unsupported candidate findings, directly repairs accepted findings, verifies repairs, and repeats until `accepted = 0` with no unresolved findings. After convergence, one skill-owned independent Reviewer is optional only when the strict structural capability gate passes; otherwise no Reviewer is created.
 
-The Code Review execution boundary is absolute for this phase:
+The Code Review execution boundary is closed for this phase:
 
-- Do not delegate any review work directly or indirectly.
-- Do not invoke another review skill or review workflow.
-- Do not use a general-purpose execution unit for review or relabel delegated work as a finder, verifier, audit, compatibility review, verification, or gap sweep.
+- Do not delegate the mandatory Main-Agent review or invoke another review skill or workflow.
+- Do not add review execution outside the single optional Reviewer owned and gated by `prizmkit-code-review`.
+- The optional Reviewer must be structurally read-only, unable to execute arbitrary commands or downstream execution, and natively resumable as the same unit; otherwise strict downgrade applies.
 - Direct reading, searching, editing, and testing by the current Main Agent remain allowed.
 - `review-report.md` is the only persisted review artifact; do not append separate Review Notes to another artifact.
 

package/bundled/dev-pipeline/templates/sections/bugfix-session-status.md

@@ -28,4 +28,4 @@ Before exiting, write the session status file:
 }
 ```
 
-For fresh manual/hybrid partial stops, set `status="partial"`, `can_resume=true`, and `resume_from_phase=4`.
+For manual/hybrid verification, record the selected automated verification method and evidence in `manual_verification_policy`; never use a partial stop solely because the plan labels verification as manual or hybrid.

package/bundled/dev-pipeline/templates/sections/context-budget-rules.md

@@ -6,7 +6,7 @@ You are running in **headless non-interactive mode** with a FINITE context windo
 
 1. **context-snapshot.md is your single source of truth** — After it is available, use it instead of re-reading individual source files. If you just created or updated it in this session, continue from the in-context content; read it only when resuming/continuing, after context compaction/loss, or when handing work to a subagent.
 2. **Never re-read your own writes** — After you create/modify a file, do NOT read it back to verify. Trust your write was correct.
-3. **Never re-read unmodified files** — Once you have read a file into context, do NOT read it again unless it was modified by an Edit/Write operation after your last read. Use platform file/search tools for targeted lookup; when shell-free helper lookup is needed, run `{{RUNTIME_HELPER_CMD}} text search <file> --pattern "<pattern>" --json`, then read only the smallest bounded range with the platform file-reading tool instead of full-file Read. Before issuing a Read, ask yourself: "Have I read this file before, and has it changed since?" If the answer is "no, it hasn't changed" — do NOT read it. This applies to all files summarized in context-snapshot.md Section 4. Normal work delegation outside Code Review must receive context-snapshot.md and rely on it rather than independently re-reading files the Main Agent already read. Code Review is excluded from normal work delegation and runs only in the current Main Agent.
+3. **Never re-read unmodified files** — Once you have read a file into context, do NOT read it again unless it was modified by an Edit/Write operation after your last read. Use platform file/search tools for targeted lookup; when shell-free helper lookup is needed, run `{{RUNTIME_HELPER_CMD}} text search <file> --pattern "<pattern>" --json`, then read only the smallest bounded range with the platform file-reading tool instead of full-file Read. Before issuing a Read, ask yourself: "Have I read this file before, and has it changed since?" If the answer is "no, it hasn't changed" — do NOT read it. This applies to all files summarized in context-snapshot.md Section 4. Normal work delegation outside the optional skill-owned review contract must receive context-snapshot.md and rely on it rather than independently re-reading files the Main Agent already read. Code Review keeps mandatory Main-Agent ownership and may use only its strict-gated skill-owned Reviewer after convergence.
 4. **Stay focused** — Do NOT explore code unrelated to this feature. No curiosity-driven reads.
 5. **One task at a time** — Complete and test one task before starting the next.
 6. **Minimize tool output** — Never load full command output into context. First capture command output to a temp file using the command/tool output option or the host-appropriate redirection, then inspect only the final relevant lines and use targeted search helpers to extract the information needed for the current task. Only read the filtered result — never the raw full output.

package/bundled/dev-pipeline/templates/sections/headless-commit-authorization.md

@@ -8,9 +8,8 @@ The pipeline launch has already authorized local commits for this task. Invoke `
 {
   "mode": "l4-headless",
   "owner": "prizmkit-l4",
-  "local_commit_authorized": true,
-  "push_authorized": false
+  "local_commit_authorized": true
 }
 ```
 
-The committer must still verify every lifecycle gate, inspect the intended diff, generate a Conventional Commit message, stage only intended files, create the local commit, and verify it. It must never push. If the execution context is absent or invalid, mark the task blocked and exit; do not ask the user.
+The committer must still verify every lifecycle gate, inspect the intended diff, generate a Conventional Commit message, stage only intended files, create the local commit, and verify it. Remote publication is controlled by the runtime after the local commit; do not make a publication decision in this session. If the execution context is absent or invalid, mark the task blocked and exit; do not ask the user.

package/bundled/dev-pipeline/templates/sections/phase-commit-full.md

@@ -27,7 +27,7 @@ git add .prizmkit/prizm-docs/
 
 **d.** Run `/prizmkit-committer` → THE ONLY commit for this feature:
 `feat({{FEATURE_ID}}): {{FEATURE_TITLE}}`
-This single commit includes: feature code + tests + .prizmkit/prizm-docs/ updates. Do NOT push.
+This single commit includes: feature code + tests + .prizmkit/prizm-docs/ updates.
 - MANDATORY: commit must be done via `/prizmkit-committer` skill. Do NOT run manual `git add`/`git commit` as a substitute.
 - Do NOT run `update-feature-status.py` here — the pipeline runner handles feature-list.json updates automatically after session exit.
 
@@ -72,4 +72,4 @@ After all of the following are true, the session is **TERMINAL**:
 - `.prizmkit/specs/{{FEATURE_SLUG}}/completion-summary.json` is written
 - the `prizmkit-committer` checkpoint is marked `completed`
 
-At that point, stop immediately. Do **not** process delayed normal-work results, edit files, amend the commit, or start any new tool calls. Code Review cannot have delayed delegated findings because it runs only in the current Main Agent. Any normal-work result that arrives after S09 is completed is follow-up work for a later session, not part of this feature commit.
+At that point, stop immediately. Do **not** process delayed normal-work results, edit files, amend the commit, or start any new tool calls. Code Review must end its optional Reviewer lifecycle before Final Result, so no independent-review response remains pending. Any normal-work result that arrives after S09 is completed is follow-up work for a later session, not part of this feature commit.

package/bundled/dev-pipeline/templates/sections/phase-commit.md

@@ -15,7 +15,7 @@ git add .prizmkit/prizm-docs/
 
 **c.** Run `/prizmkit-committer` → THE ONLY commit for this feature:
 `feat({{FEATURE_ID}}): {{FEATURE_TITLE}}`
-This single commit includes: feature code + tests + .prizmkit/prizm-docs/ updates. Do NOT push.
+This single commit includes: feature code + tests + .prizmkit/prizm-docs/ updates.
 - MANDATORY: commit must be done via `/prizmkit-committer` skill. Do NOT run manual `git add`/`git commit` as a substitute.
 - Do NOT run `update-feature-status.py` here — the pipeline runner handles feature-list.json updates automatically after session exit.
 
@@ -58,4 +58,4 @@ After all of the following are true, the session is **TERMINAL**:
 - `.prizmkit/specs/{{FEATURE_SLUG}}/completion-summary.json` is written
 - the `prizmkit-committer` checkpoint is marked `completed`
 
-At that point, stop immediately. Do **not** process delayed normal-work results, edit files, amend the commit, or start any new tool calls. Code Review cannot have delayed delegated findings because it runs only in the current Main Agent. Any normal-work result that arrives after S09 is completed is follow-up work for a later session, not part of this feature commit.
+At that point, stop immediately. Do **not** process delayed normal-work results, edit files, amend the commit, or start any new tool calls. Code Review must end its optional Reviewer lifecycle before Final Result, so no independent-review response remains pending. Any normal-work result that arrives after S09 is completed is follow-up work for a later session, not part of this feature commit.

package/bundled/dev-pipeline/templates/sections/phase-review-agent.md

@@ -2,13 +2,13 @@
 
 Review the completed implementation before the scoped feature test gate runs. Use `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/` so `/prizmkit-code-review` can read the spec, plan, context snapshot, implementation log, and current diff. Do not require a prior `/prizmkit-test` report here; the next phase owns the formal test gate.
 
-Run `/prizmkit-code-review` with `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/`. The skill runs a Main-Agent review loop for up to ten completed rounds. The current Main Agent is the only Code Review executor: it reviews the complete current change, rejects unsupported candidate findings, directly repairs accepted findings, verifies repairs, and repeats until `accepted = 0` with no unresolved findings.
+Run `/prizmkit-code-review` with `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/`. The skill runs a mandatory Main-Agent review loop for up to ten completed rounds: the Main Agent reviews the complete current change, rejects unsupported candidate findings, directly repairs accepted findings, verifies repairs, and repeats until `accepted = 0` with no unresolved findings. After convergence, one skill-owned independent Reviewer is optional only when the strict structural capability gate passes; otherwise no Reviewer is created.
 
-The Code Review execution boundary is absolute for this phase:
+The Code Review execution boundary is closed for this phase:
 
-- Do not delegate any review work directly or indirectly.
-- Do not invoke another review skill or review workflow.
-- Do not use a general-purpose execution unit for review or relabel delegated work as a finder, verifier, audit, compatibility review, verification, or gap sweep.
+- Do not delegate the mandatory Main-Agent review or invoke another review skill or workflow.
+- Do not add review execution outside the single optional Reviewer owned and gated by `prizmkit-code-review`.
+- The optional Reviewer must be structurally read-only, unable to execute arbitrary commands or downstream execution, and natively resumable as the same unit; otherwise strict downgrade applies.
 - Direct reading, searching, editing, and testing by the current Main Agent remain allowed.
 - `review-report.md` is the only persisted review artifact; do not append separate Review Notes to `context-snapshot.md`.
 

package/bundled/dev-pipeline/templates/sections/phase-review-full.md

@@ -2,7 +2,7 @@
 
 Review the completed implementation before the full Feature test gate runs. A review result is a required predecessor; never accept or route around testing as if a review had passed.
 
-Use `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/` so `/prizmkit-code-review` can read the spec, plan, context snapshot, implementation log, and current diff. The current Main Agent is the only Code Review executor. The skill runs a bounded Main-Agent review loop of at most ten completed internal rounds and writes only `review-report.md`. The Main-Agent review loop permits up to ten completed rounds.
+Use `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/` so `/prizmkit-code-review` can read the spec, plan, context snapshot, implementation log, and current diff. The skill runs a mandatory Main-Agent review loop of up to ten completed rounds and writes only `review-report.md`. After Main-Agent convergence, the skill may create one skill-owned independent Reviewer only when its strict structural capability gate passes; otherwise it records downgrade and creates none.
 
 - `REVIEW_PASS` → update checkpoint metadata with `stage=code-review`, `status=REVIEW_PASS`, `stage_result=REVIEW_PASS`, `next_stage=prizmkit-test`, and `resume_from=prizmkit-test`; then run the full test gate.
 - `REVIEW_NEEDS_FIXES` → preserve findings, increment the shared outer `repair_round`, route `prizmkit-implement` → `prizmkit-code-review` → `prizmkit-test`, and do not accept any test result from before the repaired review.
@@ -10,11 +10,11 @@ Use `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/` so `/prizmkit-code-review`
 
 Missing required evidence, unsafe repair, failed verification, or failure to converge by round ten produces `REVIEW_NEEDS_FIXES`.
 
-The Code Review execution boundary is absolute:
+The Code Review execution boundary is closed:
 
-- Do not delegate any review work directly or indirectly.
-- Do not invoke another review skill or review workflow.
-- Do not use a general-purpose execution unit for review or relabel delegated work as a finder, verifier, audit, compatibility review, verification, or gap sweep.
+- Do not delegate the mandatory Main-Agent review or invoke another review skill or workflow.
+- Do not add review execution outside the single optional Reviewer owned and gated by `prizmkit-code-review`.
+- The optional Reviewer must be structurally read-only, unable to execute arbitrary commands or downstream execution, and natively resumable as the same unit; otherwise strict downgrade applies.
 - Direct reading, searching, editing, and testing by the current Main Agent remain allowed.
 - `review-report.md` is the only persisted review artifact; do not append separate Review Notes to `context-snapshot.md`.
 

package/bundled/dev-pipeline/templates/sections/refactor-phase-commit-report.md

@@ -14,7 +14,7 @@ Run `/prizmkit-committer` with commit prefix:
 refactor({{REFACTOR_ID}}): {{REFACTOR_TITLE}}
 ```
 
-Do not push.
+The runtime controls any optional remote publication after this local commit; do not make a publication decision in this session.
 
 Write `.prizmkit/refactor/{{REFACTOR_ID}}/refactor-report.md` with:
 - refactor summary;

package/bundled/dev-pipeline/templates/sections/refactor-phase-review.md

@@ -1,12 +1,12 @@
 ### Phase 3: Review — Code Review & Behavior Verification
 
-Run `/prizmkit-code-review` directly with `artifact_dir=.prizmkit/refactor/{{REFACTOR_ID}}/`. The skill runs a Main-Agent review loop for up to ten completed rounds. The current Main Agent is the only Code Review executor: it reviews the complete current change, rejects unsupported candidate findings, directly repairs accepted findings, verifies repairs, and repeats until `accepted = 0` with no unresolved findings.
+Run `/prizmkit-code-review` directly with `artifact_dir=.prizmkit/refactor/{{REFACTOR_ID}}/`. The skill runs a mandatory Main-Agent review loop for up to ten completed rounds: the Main Agent reviews the complete current change, rejects unsupported candidate findings, directly repairs accepted findings, verifies repairs, and repeats until `accepted = 0` with no unresolved findings. After convergence, one skill-owned independent Reviewer is optional only when the strict structural capability gate passes; otherwise no Reviewer is created.
 
-The Code Review execution boundary is absolute for this phase:
+The Code Review execution boundary is closed for this phase:
 
-- Do not delegate any review work directly or indirectly.
-- Do not invoke another review skill or review workflow.
-- Do not use a general-purpose execution unit for review or relabel delegated work as a finder, verifier, audit, compatibility review, verification, or gap sweep.
+- Do not delegate the mandatory Main-Agent review or invoke another review skill or workflow.
+- Do not add review execution outside the single optional Reviewer owned and gated by `prizmkit-code-review`.
+- The optional Reviewer must be structurally read-only, unable to execute arbitrary commands or downstream execution, and natively resumable as the same unit; otherwise strict downgrade applies.
 - Direct reading, searching, editing, and testing by the current Main Agent remain allowed.
 - `review-report.md` is the only persisted review artifact; do not append separate Review Notes to another artifact.
 

package/bundled/dev-pipeline/templates/sections/refactor-reminders.md

@@ -3,7 +3,7 @@
 - Use L1 skills: `/prizmkit-plan`, `/prizmkit-implement`, `/prizmkit-code-review`, `/prizmkit-retrospective`, `/prizmkit-committer`.
 - All refactor skills use `artifact_dir=.prizmkit/refactor/{{REFACTOR_ID}}/`.
 - Behavior preservation is the first priority.
-- Do not spawn a top-level Dev implementation subagent; Code Review runs only in the current Main Agent without delegation.
+- Do not spawn a top-level Dev implementation subagent; Code Review keeps mandatory Main-Agent ownership and may use only its strict-gated skill-owned Reviewer after convergence.
 - Main orchestrator runs `/prizmkit-code-review` directly.
 - Commit with `refactor(<scope>):`, not `feat:` or `fix:`.
 - Checkpoint state is the recovery truth; skipped steps must be marked `skipped`.

package/bundled/dev-pipeline/templates/sections/subagent-timeout-recovery.md

@@ -1,6 +1,6 @@
 ## Normal Work Delegation Timeout Recovery
 
-This recovery path applies only to normal work delegated outside Code Review. Code Review never uses delegated execution or this retry procedure.
+This recovery path applies only to normal work delegated outside the optional skill-owned review contract. Code Review never applies this retry procedure to its independent Reviewer; Reviewer creation or native-resume failure uses the skill's strict downgrade instead.
 
 If a normal work execution unit times out:
 1. `{{RUNTIME_HELPER_CMD}} artifact list .prizmkit/specs/{{FEATURE_SLUG}}` — check what exists

package/bundled/dev-pipeline/templates/sections/task-contract.md

@@ -8,6 +8,10 @@ Implement {{FEATURE_ID}}: "{{FEATURE_TITLE}}".
 
 {{FEATURE_DESCRIPTION}}
 
+### User Context
+
+{{USER_CONTEXT}}
+
 ### Scope Rule
 
 Current scope is limited to the intersection of:

package/bundled/dev-pipeline/tests/test_generate_bootstrap_prompt.py

@@ -51,9 +51,9 @@ FORBIDDEN_THREE_STRIKE = "3-" + "strike"
 FORBIDDEN_TWENTY_STEP = "20-" + "step window"
 
 REVIEW_PROMPT_REQUIRED = (
-    "The current Main Agent is the only Code Review executor",
-    "Do not invoke another review skill or review workflow",
-    "finder, verifier, audit, compatibility review, verification, or gap sweep",
+    "mandatory Main-Agent review",
+    "strict structural capability gate",
+    "skill-owned independent Reviewer",
     "`review-report.md` is the only persisted review artifact",
 )
 
@@ -1235,10 +1235,10 @@ class TestDirectOrchestratorImplementationPrompts:
             assert FORBIDDEN_TEST_CMD_PLACEHOLDER not in rendered
             assert FORBIDDEN_THREE_STRIKE not in rendered
             assert FORBIDDEN_TWENTY_STEP not in rendered
-            assert "Main-Agent review loop" in rendered
+            assert "mandatory Main-Agent review" in rendered
             assert "up to ten completed rounds" in rendered
-            assert "The current Main Agent is the only Code Review executor" in rendered
-            assert "Do not invoke another review skill or review workflow" in rendered
+            assert "strict structural capability gate" in rendered
+            assert "skill-owned independent Reviewer" in rendered
             assert "low=0" not in rendered
             assert "Reviewer 3" not in rendered
 
@@ -1366,9 +1366,19 @@ class TestContinuationHandoff:
         assert checkpoint_cursor(checkpoint)["first_cursor"] == "S02 (active)"
 
 
-# ---------------------------------------------------------------------------
-# F-033 headless prompt cleanup and platform-aware paths
-# ---------------------------------------------------------------------------
+def test_modular_feature_prompt_renders_user_context(tmp_path):
+    prompt = _render_feature_prompt(
+        tmp_path / "user-context",
+        mode="standard",
+        user_context=["Use the existing event envelope", "Keep the public API backward compatible"],
+    )
+
+    assert "Use the existing event envelope" in prompt
+    assert "Keep the public API backward compatible" in prompt
+    assert "These materials were provided by the user" in prompt
+    assert "{{USER_CONTEXT}}" not in prompt
+
+
 
 HEADLESS_FORBIDDEN_PROMPT_STRINGS = [
     "### Interactive Claude Code Note",
@@ -1389,7 +1399,7 @@ def _write_feature_list(path, feature):
     path.write_text(json.dumps({"features": [feature], "global_context": {"language": "Python"}}), encoding="utf-8")
 
 
-def _render_feature_prompt(tmp_path, mode="standard", template=None, platform="claude", browser_interaction=None, complexity=None):
+def _render_feature_prompt(tmp_path, mode="standard", template=None, platform="claude", browser_interaction=None, complexity=None, user_context=None):
     project = tmp_path / "project"
     project.mkdir(parents=True)
     (project / ".prizmkit" / "plans").mkdir(parents=True)
@@ -1403,6 +1413,8 @@ def _render_feature_prompt(tmp_path, mode="standard", template=None, platform="c
         "estimated_complexity": complexity or {"lite": "low", "standard": "medium", "full": "high"}[mode],
         "acceptance_criteria": ["Prompts are clean"],
     }
+    if user_context is not None:
+        feature["user_context"] = user_context
     if browser_interaction is not None:
         feature["browser_interaction"] = browser_interaction
     feature_list = project / ".prizmkit" / "plans" / "feature-list.json"
@@ -1801,28 +1813,29 @@ class TestBrowserOptInPromptPolicy:
         assert "browser-verification" not in self._checkpoint_skills(tmp_path / "global-disable" / "bugfix", "bugfix")
         assert "browser-verification" not in self._checkpoint_skills(tmp_path / "global-disable" / "refactor", "refactor")
 
-    def test_fresh_manual_bugfix_prompt_stops_before_commit_phase(self, tmp_path):
+    def test_manual_bugfix_prompt_remains_headless_and_committable(self, tmp_path):
         prompt = _render_bugfix_prompt(
-            tmp_path / "fresh-manual-bugfix",
+            tmp_path / "manual-bugfix",
             bug_overrides={"verification_type": "manual"},
         )
 
         assert "Manual / Hybrid Verification Gate" in prompt
-        assert "Stop before `/prizmkit-retrospective` and `/prizmkit-committer`" in prompt
-        assert "### Phase 4: Commit & Learn" not in prompt
-        assert "Run `/prizmkit-committer` with commit prefix" not in prompt
+        assert "must complete manual/hybrid verification automatically" in prompt
+        assert "Stop before `/prizmkit-retrospective` and `/prizmkit-committer`" not in prompt
+        assert "### Headless Commit Authorization" in prompt
+        assert "status=\"partial\"" not in prompt
 
-    def test_recovery_manual_bugfix_prompt_includes_commit_phase_with_substitution_policy(self, tmp_path):
+    def test_recovery_manual_bugfix_uses_same_automatic_policy(self, tmp_path):
         prompt = _render_bugfix_prompt(
             tmp_path / "recovery-manual-bugfix",
             bug_overrides={"verification_type": "manual"},
             retry_count="1",
         )
 
-        assert "Manual / Hybrid Verification Gate" not in prompt
-        assert "Recovery-class session: automated verification may substitute for manual/hybrid UAT" in prompt
-        assert "### Phase 4: Commit & Learn" in prompt
-        assert "Run `/prizmkit-committer` with commit prefix" in prompt
+        assert "Manual / Hybrid Verification Gate" in prompt
+        assert "must complete manual/hybrid verification automatically" in prompt
+        assert "Recovery-class session: automated verification may substitute" not in prompt
+        assert "### Headless Commit Authorization" in prompt
 
 
 class TestHeadlessPromptCleanupF033:
@@ -1918,9 +1931,9 @@ class TestHeadlessPromptCleanupF033:
         refactor_prompt = _render_refactor_prompt(tmp_path / "refactor-mixed", platform="claude")
 
         assert "{{" + "REVIEWER_" + "SUBAGENT_PATH" + "}}" not in replacements
-        assert "Main-Agent review loop" in refactor_prompt
-        assert "The current Main Agent is the only Code Review executor" in refactor_prompt
-        assert "Do not invoke another review skill or review workflow" in refactor_prompt
+        assert "mandatory Main-Agent review" in refactor_prompt
+        assert "strict structural capability gate" in refactor_prompt
+        assert "skill-owned independent Reviewer" in refactor_prompt
         assert "Reviewer 3" not in refactor_prompt
 
     def test_bugfix_refactor_explicit_codex_override(self, tmp_path, monkeypatch):
@@ -1942,9 +1955,9 @@ class TestHeadlessPromptCleanupF033:
         refactor_prompt = _render_refactor_prompt(tmp_path / "refactor-codex", platform="claude", explicit_platform="codex")
 
         assert "{{" + "REVIEWER_" + "SUBAGENT_PATH" + "}}" not in replacements
-        assert "Main-Agent review loop" in refactor_prompt
-        assert "The current Main Agent is the only Code Review executor" in refactor_prompt
-        assert "Do not invoke another review skill or review workflow" in refactor_prompt
+        assert "mandatory Main-Agent review" in refactor_prompt
+        assert "strict structural capability gate" in refactor_prompt
+        assert "skill-owned independent Reviewer" in refactor_prompt
         assert "Reviewer 3" not in refactor_prompt
 
 

package/bundled/dev-pipeline/tests/test_generate_bugfix_prompt.py

@@ -320,7 +320,7 @@ def test_template_source_is_clean_for_headless_prompt_contract():
     assert "prizmkit-workflow" not in content
     assert "/prizmkit-test scope=this-change artifact_dir=.prizmkit/bugfix/{{BUG_ID}}/" in content
     assert "local_commit_authorized=true" in content
-    assert "push_authorized=false" in content
+    assert "push_authorized" not in content
 
 
 def test_bugfix_prompt_keeps_fine_grained_phases_out_of_external_status_contract():
@@ -559,18 +559,15 @@ class TestBugfixCheckpointGeneration:
         assert metadata["repair_round"] == 2
         assert metadata["resume_from"] == "prizmkit-implement"
 
-    def test_manual_bugfix_keeps_test_gate_but_omits_commit_authorization(self):
-        sections_dir = Path("dev-pipeline/templates/sections")
+    def test_manual_bugfix_uses_automatic_verification_and_keeps_commit_gate(self):
         sections = assemble_bugfix_sections(
-            "standard", str(sections_dir), False, True,
+            "standard", "dev-pipeline/templates/sections", False, True,
         )
         names = [name for name, _ in sections]
 
-        assert "bugfix-phase-review" in names
-        assert "bugfix-phase-test" in names
         assert "bugfix-manual-gate" in names
-        assert "headless-commit-authorization" not in names
-        assert "bugfix-phase-commit-report" not in names
+        assert "headless-commit-authorization" in names
+        assert "bugfix-phase-commit-report" in names
 
     def test_rendered_bugfix_prompt_is_atomic_headless_and_local_commit_only(self, tmp_path):
         prompt = _render_bugfix_prompt(tmp_path)
@@ -581,10 +578,10 @@ class TestBugfixCheckpointGeneration:
         assert "FAST_PATH=true" not in prompt
         assert "prizmkit-workflow" not in prompt
         assert '"local_commit_authorized": true' in prompt
-        assert '"push_authorized": false' in prompt
+        assert "push_authorized" not in prompt
         assert "Do not ask questions, wait for user input" in prompt
+        assert "Remote publication is controlled by the runtime" in prompt
         assert "push_authorized\": true" not in prompt
-        assert "automatic push" not in prompt.lower()
         assert ".prizmkit/bugfix/B-001/" in prompt
 
     def test_setup_section_skips_and_finalization_group_expands(self):

package/bundled/dev-pipeline/tests/test_generate_refactor_prompt.py

@@ -214,7 +214,7 @@ def test_template_source_is_clean_for_headless_prompt_contract():
     assert "prizmkit-workflow" not in content
     assert "/prizmkit-test scope=this-change artifact_dir=.prizmkit/refactor/{{REFACTOR_ID}}/" in content
     assert "local_commit_authorized=true" in content
-    assert "push_authorized=false" in content
+    assert "push_authorized" not in content
     assert "Behavior-preservation checks remain supporting evidence" in content
 
 
@@ -399,8 +399,8 @@ class TestRefactorCheckpointGeneration:
         assert "prizmkit-workflow" not in prompt
         assert "Behavior-preservation checks collected during planning and implementation remain supporting evidence" in prompt
         assert '"local_commit_authorized": true' in prompt
-        assert '"push_authorized": false' in prompt
-        assert "Do not ask questions, wait for user input" in prompt
+        assert "push_authorized" not in prompt
+        assert "Remote publication is controlled by the runtime" in prompt
         assert "automatic push" not in prompt.lower()
         assert "push_authorized\": true" not in prompt